© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 380
    Prev
    Next
    INDEX
    Explanations

    cooking and baking instructions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Instructions for dough or batter preparation

    np_acts-logits-general · gemini-2.0-flash

    mixing dough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.73
    ngdoc
    -0.72
    XmlAccessType
    -0.72
    EndGlobalSection
    -0.69
    /**
    -0.67
    SequentialGroup
    -0.64
    ⓧ
    -0.61
    Gön
    -0.60
    TypedDataSet
    -0.59
    Française
    -0.58
    POSITIVE LOGITS
     mixing
    0.84
     Mixing
    0.79
     mixer
    0.78
    Mixing
    0.76
    mixing
    0.67
     dough
    0.67
    mixer
    0.65
    Mixer
    0.63
     kne
    0.63
     Mixer
    0.60
    Activations Density 0.118%

    No Known Activations